Senior AI Engineer

We're recruiting on behalf of a global SaaS business in the risk, compliance and safety-management space, helping organisations manage contractor risk across high-hazard industries worldwide. It's a business built on change, fast-growing, acquisitive, and genuinely global in reach, with a strong internal promotion culture and a lot of momentum behind its product and technology roadmap right now. What the role involves We're hiring the founding engineer for a brand-new Agentic Workforce team, reporting into the VP of Data \& AI. This team owns the company's entire approach to internal AI agents, from individual and team-level agent builds through to fully autonomous, production-grade "gold standard" agents operating in high-risk, regulated parts of the business. You'll design, build and deploy production-grade AI agents that automate multi-step operational workflows, orchestrating LLMs, tools, memory and business logic, while also helping define the governance, evaluation and guardrail standards that the rest of the business builds against. It's a genuinely dual-function role: hands-on agent architecture and build, plus real influence over how agentic AI gets adopted safely across the organisation. The role is highly stakeholder-facing. You'll work directly with teams across the business to understand operational pain points and turn them into reliable, production-grade agentic solutions, so as much as this is a deep technical build role, strong communication and the ability to work with non-technical stakeholders really matters. What we're looking for * Strong technical foundation in Python and backend/API development * Hands-on experience building LLM-based solutions and agentic systems, including orchestration frameworks (e.g. LangGraph, LangChain, Microsoft Agent Framework, CrewAI or similar) * Experience designing agents that reason, plan, use tools and maintain state/memory to complete multi-step tasks * Comfortable with cloud infrastructure (AWS preferred, not essential) for deploying and scaling agentic systems * Experience with prompt engineering, embeddings and RAG * Experience defining agent evaluation, guardrails and observability for safe production behaviour * Familiarity with containerisation (Docker, Kubernetes or similar) * Proven ability to work directly with business stakeholders and translate requirements into shipped, production solutions *This role can be hybrid across a number of locations, or remote-first (with monthly travel)*